ウェーブレットポリシー：世界事前記憶を用いたスケール領域での模倣学習
Wavelet Policy: Imitation Learning in the Scale Domain with World Prior Memory
背景画像から持続的なシーン構造を記憶トークンとして符号化し、ウェーブレット変換で行動をマルチスケールに分解して予測する軽量な模倣学習フレームワークを提案。実機を含む多数のタスクで高精度を達成。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Changchuan Yang, Haoxuan Xu, Yuhang Dong, Guanzhong Tian, Haizhou Ge, Hongrui Zhu
分類: cs.RO
原文アブストラクト
Conventional visuomotor imitation learning usually predicts future robot actions directly in the time domain. Such formulations often have limited physical scene awareness and weak memory. In this work, we propose Wavelet Policy, a lightweight imitation learning framework that combines World Prior Memory (WPM) with wavelet-based multi-scale action modeling. Our key idea is to encode persistent physical scene structure from static background images into compact memory tokens, which are fused into world-prior tokens and injected into the encoder during forward propagation. Based on this memory-conditioned representation, we further perform wavelet-domain decomposition over horizon-aligned latent action tokens and adopt a Single-Encoder Multiple-Decoder (SE2MD) architecture to model latent components at different temporal scales. The resulting latent subbands are reconstructed through inverse wavelet transform and finally projected into executable action chunks. To facilitate efficient world prior learning, we introduce a world-prior adaptation loss, encouraging the background encoder to retain persistent scene knowledge while remaining lightweight and stable. Extensive experiments on four simulated and six real-world robotic manipulation tasks show that Wavelet Policy consistently outperforms strong baselines. These results demonstrate that combining scale-domain action modeling with world-prior memory provides an effective and efficient solution for embodied manipulation.
